Characterization of urban built and natural environments with high-resolution satellite images and unsupervised deep learning
Bibliographic record
Abstract
BACKGROUND AND AIM: Cities in the developing world are expanding rapidly and undergoing changes to their roads, housing and other buildings, vegetation, and land use characteristics. Timely data are needed to ensure that urban change enhance health, wellbeing and sustainability. METHODS: We characterise, as mutually exclusive clusters, the complex, multidimensional, built and natural environments in cities with high-resolution satellite images and unsupervised deep clustering. We apply our approach to Accra, Ghana, one of the fastest growing cities in the developing world, and contextualise the resultant clusters with demographic and environmental data that were not used for clustering. RESULTS: We show that image-based clusters captured distinct features of the urban built environment (building count, size, density, and orientation; length and arrangement of roads), vegetation, water, and population, either as a unique defining characteristic (e.g., bodies of water or dense vegetation) or in combination (e.g., buildings surrounded by vegetation or sparsely populated areas intermixed with roads). Clusters that were based on single defining characteristics were robust to the spatial scale of analysis and choice of cluster number, whereas those based on a combination of defining characteristics changed based on scale and number of clusters. CONCLUSION: The results demonstrate that satellite data and unsupervised deep learning provide a cost-effective interpretable and scalable approach for real-time tracking of sustainable urban development, especially where traditional environmental and demographic data are limited and not frequently updated. Our approach has multiple urban environmental applications, such as providing ground data for tracking and measuring urban health, air- and noise pollution, urban connectivity and road traffic, as well as city growth in cities across Africa and beyond. KEYWORDS: Big data, satellite imagery, deep learning, built environment; urban growth, unsupervised machine learning
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".